From material to course
Paste text, upload PowerPoint or PDF, or just write a request. The AI turns it into detailed material, then into slides with diagrams, pictures and notes.
AI LMS · Learning with an AI lecturer
Paste a document, a process or a job description. The AI LMS writes the slides, teaches each part by voice, answers questions, quizzes and grades, then shows you who studied, how far they got and what they scored.
Learners only need a link · Nothing to install
Features
Writing, teaching, testing and tracking learners, all in one place.
Paste text, upload PowerPoint or PDF, or just write a request. The AI turns it into detailed material, then into slides with diagrams, pictures and notes.
It teaches slide by slide, stops when a learner asks, answers, then carries on. Learners ask by voice or by typing.
Questions from the lesson; the AI grades each answer and notes strengths and what to review. Set a pass mark, allow a retake.
Learners sign in or type their name. See who took which lesson, for how long, how far and with what score, and download it as CSV.
Try one
Open one and learn with the AI lecturer right away.
Integration
Already run a learning system? Bring AI lessons into your courses with the LTI 1.3 standard.
Set up the connection →AI Voice · Vietnamese speech AI platform
Accurate, real-time Vietnamese speech-to-text, text-to-speech and LLM — from a team that has deployed voice AI for hundreds of enterprises in Vietnam, the USA, Mexico, the Philippines and Thailand.
Internal figures, measured on data not used for training — see how they are measured
One account, one API key for every service.
Deployment experience in Vietnam USA Mexico Philippines Thailand
Accuracy
Word error rate (WER, lower is better) of AIVISION's model on four Vietnamese test sets, including medical conversations and real business meetings.
VLSP test set (1,000 utterances, 1.76 h, human references).
| Test set | Content | AIVISION WER |
|---|---|---|
| FLEURS-vi | Read speech | 3.60% |
| VIVOS | Read speech, many speakers | 4.71% |
| ViMedCSS | Medical, with English terms | 14.10% |
| AIV meetings | Real business meetings | 19.71% |
| Average | 10.53% |
AIVISION internal results on data not used for training. ViMedCSS: medical conversations with English terms; AIV meetings: real business meetings.
Why AIVISION
A 690,517-hour Vietnamese speech corpus, trained on a 24× H200 GPU cluster for over 500 hours — tones, three regional accents, fast speech, English mixed in.
Words appear while the speaker is still talking; AI voices start on the first word.
Deployed for hundreds of enterprises in Vietnam, the USA, Mexico, the Philippines and Thailand.
Industries
For developers
Get an API key in the console, send audio, get text back. The language model speaks the OpenAI API — switch the base URL and go.
API docs →# Speech-to-Text: a file in, text out
curl https://s2speech.com/v1/transcribe \
-H "Authorization: Bearer $AIVISION_KEY" \
-F file=@cuoc-hop.mp3 -F language=vi
# LLM: OpenAI-compatible
from openai import OpenAI
client = OpenAI(base_url="https://s2speech.com/v1", api_key=AIVISION_KEY)
reply = client.chat.completions.create(model="aivision-L1.0",
messages=[{"role": "user", "content": "Tóm tắt cuộc họp này..."}])
The person behind AIVISION
CEO, AIVISION
Dr. Giang Vo leads AIVISION in building a speech AI platform for Vietnamese — from the data and recognition models to the voices and the apps — and works directly with customers on their deployments.
Blog
Discover a 4-step workflow to automate enterprise meeting minutes. Learn how AI transforms audio recordings into precise, searchable, and actionable summaries.
Discover how to integrate speech-to-text, text-to-speech, and LLM APIs to build a responsive voice assistant. This guide provides practical Python and JavaScript code for a full-stack implementation.
Explore critical strategies for securing voicebot systems. Learn how to protect sensitive data throughout the STT and LLM processing pipeline.
AI LMS
Make your first lesson in minutes and send learners the link, or talk to Dr. Giang Vo directly.
No. Every service is free, no card needed. Each account has a daily usage limit that resets at midnight; if you need more, contact an admin.
s2speech is AIVISION's speech AI platform: Speech-to-Text, Text-to-Speech and the aivision-L1.0 language model, plus ready-made apps such as Voice Note, Live Translate and Multilingual Meetings.
On four Vietnamese test sets (FLEURS-vi, VIVOS, ViMedCSS and real business meetings) AIVISION's model averages a 10.53% word error rate, measured on data not used for training.
Vietnamese first, plus English; the translation and meeting apps support 24 languages including Spanish, Filipino, Thai, Chinese, Japanese, Korean and Indonesian.
Create an API key in the console and call the REST or WebSocket API. The language model is OpenAI-compatible, so familiar SDKs work as they are.